© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5460
    Prev
    Next
    INDEX
    Explanations

    fluor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.70
     CreateTagHelper
    -0.68
    ährend
    -0.67
    ResumeLayout
    -0.65
    AndroidJUnit
    -0.63
     propOrder
    -0.63
     createState
    -0.63
    parsedMessage
    -0.62
    fjspx
    -0.61
    piram
    -0.60
    POSITIVE LOGITS
    abetes
    0.54
     الحره
    0.50
    Bangkok
    0.46
     Salgado
    0.46
     Vancouver
    0.46
     Antarctic
    0.45
    ależ
    0.45
     Shet
    0.44
     talaga
    0.44
    essions
    0.43
    Activations Density 0.020%

    No Known Activations